Models

llama3.2_1b_16bit

Grogros-dmWM-Llama-3.2-1B-Instruct-M-A-O-d4-a0.25-learnability_adv

llama1B_OB100

dmWM-llama-3.2-1B-Instruct-KGWB-OWT_WMBoundary-OWT-WB-v3

RS_1B_RM_iter1

AIAutocad

Llama-3.2-1B-Instruct-terapeutico

Llama-3.2-1B_ClinicalWhole_it.layer1_NoQuant_64_16_0.01_16CLINICALe3c-sentences_tag

llama-3.2-1B-sutdqa-merged

dmWM-llama-3.2-1B-Instruct-OWTWM-DistillationWM-OWTWM2-wmToken-d4-10percent

dmWM-llama-3.2-1B-Instruct-WOHealth-d4-NoReg

llama3.2-1b-neuspell-5epochs

finetune-llama-3.2-1b-math50k

Llama-3.2-1B-Instruct_sum_PPO_Skywork_177k_2_1ep

6_bitwise_MQA_llama_model

12_layer_MQA_llama_model

10_first_MQA_llama_model

third_fully_merged

llama32_1bi_CoTsft_rs0_3_5cut_gem3_e2

translator-llama

llama-31-hhrlhf-squad-rlhf-policy-model

Llama-3.2-1B-Instruct_AllDataSources_8e-06_constant_512

Mixmix-LlaMAX3.2-1B-Merge

Llama-3.2-1B-Instruct_sum_KTO_20k_2_1ep

Cerberus-3.2-1B

llama32_1b_scoring_all_tasks

Llama3.2.1B.0.1-L

Llama-3.2-1B-Instruct_ORPO_1

1_layer_MQA_llama_model

Llama-3.2-1B_AllDataSourcesClinical_0.0002_cosine_512_paper

Llama-3.2-1B-Instruct_sum-10k_2Mar-2025_A100

Llama-3.2-1B_AllDataSources_8e-06_constant_0.3_512_tp

10_layer_MQA_llama_model

Llama-3.2-1B_AllDataSources_it.layer1_NoQuant_64_32_0.01_16CLINICALe3c-sentences_tag

llamapretrained1

Llama-3.2-1B-Instruct_sum_PPO_Skywork_40.0k_1_1ep

16_first_MQA_llama_model

Llama-3.2-1B_3_mix_position_biased_unbiased

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_IdkDPO_lr5e-05_beta0.5_alpha2_epoch5

llama3_1B_hh_reject_2

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_NPO_lr1e-05_beta0.5_alpha2_epoch5

tfa_output_2025_m05_d10_t20h_16m_03s